Devices, systems and processes for the detection of unsafe cabin conditions that provides a safer passenger experience in autonomous vehicles are described. One example method for enhancing passenger safety includes capturing at least a set of images of one or more passengers in the vehicle, determining, based on the set of images, the occurrence of an unsafe activity in an interior of the vehicle, performing, using a neural network, a classification of the unsafe activity, and performing, based on the classification, one or more responsive actions.

A motor vehicle (1) has a driver’s seat (8) which is assigned a safety belt (20) for a driver. The safety belt (20) here is held on a pivotable bracket (13). This bracket (13) is pivotable between a releasing position, which permits entry, and a restraining position, which protects the driver. The bracket (13) here is disposed in such a manner that said bracket (13) in the releasing position holds the safety belt (20) in a position in which the latter impedes the driver. In order to avoid any impediment of the driver in the restraining position of the bracket (13), the bracket (13) above the driver’s seat is elbowed away from the latter. (FIG. 3)

A system for detecting improper usage of a seatbelt of a vehicle includes a vehicle seat having a seat cushion and a seat back. A shoulder belt and a lap belt are intended to restrain an occupant sitting on the vehicle seat. The system includes a sensor module associated with the shoulder belt and the lap belt. The sensor module generates signals indicative of at least one parameter associated with the vehicle seat, the shoulder belt, and the lap belt when the occupant is sitting on the vehicle seat. The system also includes a controller that receives the signals indicative of the at least one parameter associated with the seat back, the shoulder belt, and the lap belt. The controller analyzes the received one or more signals, and determines whether the seatbelt is being used improperly by the occupant, based on the analysis.

Devices, systems and processes for the detection of unsafe cabin conditions that provides a safer passenger experience in autonomous vehicles are described. One example method for enhancing passenger safety includes capturing at least a set of images of one or more passengers in the vehicle, determining, based on the set of images, the occurrence of an unsafe activity in an interior of the vehicle, performing, using a neural network, a classification of the unsafe activity, and performing, based on the classification, one or more responsive actions.

At least one analog load sensor, such as a force sensitive resistor is situated between upper and lower seat structures to generate a signal correlating with weight placed upon the seat. A vehicle has multiple seats fitted with sensors. Weight related information is communicated to a processor and an optional display, along with seatbelt latch sensor outputs to communicate to an operator if any seats are occupied without seatbelt latched. A weight force threshold for each seat is adjustable in one embodiment to customize the system to accommodate occupants of different weights and non-occupant loads of different weights. Loading information for the vehicle, such as total weight of occupants and/or objects on the seats and location of these loads upon the vehicle can be calculated and utilized to ensure that gross vehicle weight rating and load center of gravity and related parameters are within acceptable ranges.

A system includes: a first camera configured to capture first images of a driver on a driver's seat within a passenger cabin of a vehicle; a second camera configured to capture second images in front of the vehicle; a driver module configured to determine a driver of the vehicle based on at least one of the first images and to determine a present driver's licensing level of the driver with a driver's licensing body; a first detection module configured to detect first occurrences of first conditions within the passenger cabin of the vehicle based on the first images; a second detection module configured to detect second occurrences of second conditions outside of the vehicle; and a reporting module configured to, based on the present driver's licensing level of the driver, selectively generate a report including at least one of the first and second occurrences.

A seat belt attachment determining unit of a rough terrain vehicle determines whether or not a seat belt is being worn by a vehicle occupant. In the case it is determined by the seat belt attachment determining unit that the vehicle occupant is wearing the seat belt, the ECU switches a transmission gear stage of an automatic transmission using a first speed change mode. On the other hand, in the case it is determined by the seat belt attachment determining unit that the vehicle occupant is not wearing the seat belt, the ECU switches the transmission gear stage using a second speed change mode.

Systems and methods are disclosed related to restraint device (e.g., seatbelt) localization. In one embodiment, the disclosure relates to systems and methods for seatbelt detection and modeling. A vehicle may be occupied by one or more occupants wearing one or more seatbelts. A camera or other sensor is placed within the vehicle to capture images of the one or more occupants. A system analyzes the images to detect and model seatbelts depicted in the images. Specifically, the system may scan the images and areas of the images that may correspond to seatbelts. The system may assemble candidate areas of the images that may correspond to seatbelts, and refine the candidate areas based on various constraints. The system may build models based on the refined candidate areas that indicate the seatbelts. The system may visualize the models indicating the seatbelts using the images.

A system for detecting improper usage of a seatbelt of a vehicle includes a vehicle seat having a seat cushion and a seat back. A shoulder belt and a lap belt are intended to restrain an occupant sitting on the vehicle seat. The system includes a sensor module associated with the shoulder belt and the lap belt. The sensor module generates signals indicative of at least one parameter associated with the vehicle seat, the shoulder belt, and the lap belt when the occupant is sitting on the vehicle seat. The system also includes a controller that receives the signals indicative of the at least one parameter associated with the seat back, the shoulder belt, and the lap belt. The controller analyzes the received one or more signals, and determines whether the seatbelt is being used improperly by the occupant, based on the analysis.

An occupant restraint system in a self-driving vehicle, in particular a robot taxi, for customer transport, wherein the occupant restraint system provides to the customer a restraint system that can be activated by the customer to be transported, and the occupant restraint system has an analysis unit via which a check is made in a safety check as to whether or not the restraint function is activated by the customer to be transported. The analysis unit prevents the vehicle from driving if an activated restraint function is absent. A diagnostic module, with which a functional diagnostic of the functionality of the occupant restraint system can be carried out independently of the safety check, is associated with the analysis unit. In the event that a fault is present, the diagnostic module initiates a suitable service action to remedy the fault.